Related Experiment Video
Updated: Jun 5, 2025
05:17
Hybrid PET/MRI Imaging of Alzheimer's Disease Based on 18F-AV-1451
Published on: April 18, 2025
94
Multi-modal Imaging-based Pseudotime Analysis of Alzheimer progression
Bing He1, Shu Zhang2, Shannon L Risacher3
1Biomedical Engineering and Informatics, Indiana University Indianapolis, 535 W Michigan St., Indianapolis, Indiana 46202, USA, hebing@iu.edu.
Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|December 13, 2024
Summary
Understanding Alzheimer's disease (AD) progression is key for early detection. New pseudotime methods applied to imaging data show multi-modal analysis, particularly amyloid and tau, best captures disease progression over time.
Area of Science:
- Neurodegenerative disease research
- Computational biology
- Medical imaging analysis
Background:
- Alzheimer's disease (AD) is a progressive neurodegenerative disorder with no cure.
- Understanding AD progression is crucial for early detection, risk assessment, and intervention.
- Cross-sectional data typically offers only a snapshot of long, complex disease trajectories.
Purpose of the Study:
- To evaluate state-of-the-art pseudotime approaches for modeling Alzheimer's disease progression using imaging data.
- To compare pseudotime progression scores from single and multi-modal imaging in the ADNI cohort.
- To identify which imaging modalities best represent the temporal evolution of AD.
Main Methods:
- Application and comparison of various pseudotime algorithms to Alzheimer's disease imaging data.
- Evaluation of pseudotime scores derived from individual imaging modalities (e.g., MRI, PET) and multi-modal combinations.
- Analysis of the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort data.
Main Results:
- Most existing pseudotime tools showed poor generalization to imaging data, with issues like flipped progression or inadequate group separation.
- A promising pseudotime tool demonstrated that scores from both single and multi-modal imaging captured disease progression.
- Multi-modal pseudotime, unlike single modalities, validated the temporal order of imaging phenotypes and was primarily driven by amyloid and tau imaging.
Conclusions:
- Pseudotime analysis is a viable approach for modeling Alzheimer's disease progression from imaging data.
- Multi-modal imaging analysis, especially incorporating amyloid and tau, provides a more robust representation of AD's temporal trajectory.
- Future research should focus on refining pseudotime methods for neuroimaging to improve AD understanding and clinical trial design.
